Data pre-processing is a crucial but often tedious stage in research, particularly when standardising complex CSV datasets. This blog demonstrates how GenAI can systematically structure geographic location data directly from an input CSV file without coding. Our primary objective was to ensure consistent and accurate categorisation, preparing the data for
Natural Language Processing (NLP) allows us to automatically analyse and categorise textual data. With the help of GenAI, even complex classification tasks can now be executed using just a well-designed prompt. In this post, we present a practical example where GenAI classifies financial-related sentences into domain-specific categories, showcasing how effective
Making research accessible to a wider audience is no longer optional – it’s essential to academic life. Whether for public engagement, broader impact, or to ensure that essential findings reach beyond the academic bubble, science communication plays a vital role in connecting scholarship with society. One simple but effective way
Clustering refers to the unsupervised process of grouping similar entities, such as sentences, into categories based on shared characteristics without relying on predefined classes, thus revealing latent patterns in the data. For researchers, GenAI models enable this analysis without the need for programming expertise, offering a powerful means to explore
Recent advances in Generative AI offer researchers new opportunities to assign topic labels to political and legislative texts without manual coding or programming. The Comparative Agendas Project (CAP) provides a structured topic classification system that captures the major areas of public policy. Traditionally, applying these labels required manual annotation or
Time series analysis is a powerful tool for researchers across disciplines, yet its reliance on programming can pose a challenge for those without coding expertise. This blog demonstrates how AI-driven prompts can enable researchers to perform simple time series analyses without writing a single line of code, making data insights
With the rapid advancement of GenI tools, researchers now have access to innovative ways to improve their manuscripts before journal submission. One such method involves using custom GPT-based reviewers to gain preliminary feedback. To practically evaluate the usefulness of these GPT-driven reviewing tools, we tested the Scientific Paper Reviewer – ChatGPT
Collecting and reviewing relevant literature is often one of the most time-consuming parts of academic research. We tested whether this process could be faster using a single prompt with different generative AI models. To explore this, we prompted each model to return accurate academic articles on ‘legislative backsliding’. The outcome
Writing grammatically correct and stylistically sound academic texts can be a constant challenge for non-native English speakers. Fortunately, with the help of GenAI, it is now possible to review and correct scientific writing quickly and effectively. GenAI can not only detect and correct linguistic errors in seconds but also offer
Artificial Intelligence is rapidly reshaping the educational landscape, but what do we really know about its effects on learning, teaching, and classroom dynamics? With the help of GenAI, we can begin to frame research questions that tackle these complex issues head-on. In this blog, we demonstrate how GenAI can be
Today, many researchers rely on reference management tools like Mendeley, EndNote or Zotero to generate and format citations. However, there is an alternative for those who prefer not to use such software. Providing a list of references—no matter how inconsistently formatted—to a Generative AI model makes it possible
Reviewing and synthesising complex theoretical texts is a fundamental yet time-consuming aspect of academic research. Recent developments in generative AI offer new tools to assist scholars in the comparative analysis of scientific literature. This post presents a tailored prompt designed to support such work, illustrated through the example of two
